112 lines
4.5 KiB
Python
112 lines
4.5 KiB
Python
SYSTEM_PROMPT2 = """
|
|
You are an OKR coach and support us, as beginners in OKRs, with the correct phrasing of OKRs.
|
|
Always one proposal and provide the proposal in the requested format (json).
|
|
If you think the input is not clear enough and the OKR could be improved, then provide a hint,
|
|
what could be added to the user input in order to provide improved OKRs. The hint should also
|
|
always provided within the json.
|
|
|
|
Format could look like this:
|
|
{
|
|
"hint": "any additional questions, which can be added to the user input to rerun the prompting",
|
|
"proposals": [
|
|
{
|
|
"objective":"objective variant 1",
|
|
"key_results": ["key result 1"]
|
|
},
|
|
...
|
|
]
|
|
}
|
|
"""
|
|
|
|
SYSTEM_PROMPT = """
|
|
You are an OKR coach who helps beginners create well-phrased OKRs (Objectives and Key Results).
|
|
Your goal is to provide a proposal for an OKR based on user input, formatted as JSON.
|
|
If the input is unclear or incomplete, include a hint with specific questions or suggestions
|
|
to help improve the input.
|
|
|
|
Always follow this format for your response:
|
|
{
|
|
"hint": "Suggestions or questions to improve the input, if needed. If no hint is needed, return an empty string.",
|
|
"proposal": [
|
|
{
|
|
"objective": "A clear and concise objective variant",
|
|
"key_results": ["Key result 1", "Key result 2", "... up to 5 key results"]
|
|
},
|
|
...
|
|
]
|
|
}
|
|
|
|
Keep your responses concise, actionable, and aligned with OKR best practices. If you need more context from the user, ask for it in the `hint`.
|
|
Always provide a 'hint' how to further improve the user input in order to get better results.
|
|
|
|
"""
|
|
|
|
INPUT_TEMPLATE = """
|
|
We want to improve our SLA framework by finalizing the current SLA template, which is used for the negotiations with our ground service partners.
|
|
The resulting SLA will be used in order to measure the quality of the service partner and issue penalties if targets are not met.
|
|
We would like to improve this, to have a better steering function, e.g. by adding a bonus component to the SLA framework.
|
|
|
|
To achieve this, we need to develop a bonus concept which is viable, feasible and desirable.
|
|
We need to simulate the concept, so that we don't risk issuing too much bonus which we cannot cover.
|
|
We need to define organizational processes and responsibilities so that we are able to pay a bonus.
|
|
|
|
How should the OKR look like for the next cycle which starts in Jan 2025 and ends in Apr 2025?
|
|
"""
|
|
|
|
# Prompt template for user input
|
|
PROMPT_TEMPLATE = """
|
|
Please help us in defining proper OKRs.
|
|
Here is what we have thought about and we would like to phrase an OKR with up to 5 key results.
|
|
|
|
this is the user input:
|
|
{user_input}
|
|
|
|
Please provide the response in json format.
|
|
the three proposals and potentially further questions to the user to improve the OKR, should be structured in a json as response.
|
|
Objective (key: objective)
|
|
key results (list with the key results)
|
|
The json could be structured like this:
|
|
|
|
{{
|
|
"hint": "any additional questions, which can be added to the user input to rerun the prompting",
|
|
"proposals": [
|
|
{{
|
|
"objective":"objective variant 1",
|
|
"key_result_1":"key result 1",
|
|
...
|
|
}},
|
|
...
|
|
]
|
|
}}
|
|
"""
|
|
|
|
PROMPT_TEMPLATE = """
|
|
Please help us in defining proper OKRs.
|
|
Here is what we have thought about and we would like to phrase an OKR with maximum 5 key results.
|
|
|
|
this is the user input:
|
|
{user_input}
|
|
|
|
Please provide the response in json format.
|
|
"""
|
|
|
|
INPUT_TEMPLATE = """
|
|
We want to improve our SLA framework by finalizing the current SLA template, which is used for the negotiations with our ground service partners.
|
|
The resulting SLA will be used in order to measure the quality of the service partner and issue penalties if targets are not met.
|
|
We would like to improve this, to have a better steering function, e.g. by adding a bonus component to the SLA framework.
|
|
|
|
To achieve this, we need to develop a bonus concept which is viable, feasible and desirable.
|
|
We need to simulate the concept, so that we don't risk issuing too much bonus which we cannot cover.
|
|
We need to define organizational processes and responsibilities so that we are able to pay a bonus.
|
|
|
|
How should the OKR look like for the next cycle which starts in Jan 2025 and ends in Apr 2025?
|
|
"""
|
|
|
|
# Prompt template for user input
|
|
PROMPT_TEMPLATE2 = """
|
|
Please help us in defining proper OKRs.
|
|
Here is what we have thought about and we would like to phrase an OKR with up to 5 key results.
|
|
|
|
this is the user input:
|
|
{user_input}
|
|
""" |